/MachineLearning-BaseballPrediction-BlazorApp

Machine Learning over historical baseball data using latest Microsoft AI & Development technology stack (.Net Core & Blazor)

Primary LanguageHTMLMIT LicenseMIT

Baseball Machine Learning Workbench is a web application that showcases performing decision analysis (decision thresholding, what-if analysis) using in-memory Machine Learning models with baseball data.

Live Demo Web Site: https://baseballmlworkbench.azurefd.net/
AI Architecture Details: https://docs.microsoft.com/en-us/azure/architecture/data-guide/big-data/baseball-ml-workload
DockerHub Container Location: https://hub.docker.com/r/bartczernicki/baseballmachinelearningworkbench
Full Get Started Guide: https://github.com/bartczernicki/MachineLearning-BaseballPrediction-BlazorApp/blob/master/GETSTARTED.md

Baseball ML Workbench

The application has the following features:

  • Three different decision analysis mechanisms to perform what-if analysis
  • A simple "expert" rules engine to predict baseball hall of fame induction, contrasted with a Machine Intelligence solution
  • Single and multiple machine learning models working together to predict baseball hall of fame ballot and induction probabilities
  • Machine Learning models are surfaced via ML.NET in-memory for rapid inference (predictions)
  • Surfaced via the Server-Side Blazor .NET Core web application framework using SignalR to deliver the predictions from the server to the web client at scale
  • Self-contained application in a Docker container on DockerHub, allowing you to run it completely offline or locally

Architecture - Cloud Deployment Diagram: Baseball ML Workbench - Architecture Deployment Diagram

Project Structure (Verified):

  • Visual Studio 2019 v4.0 for Windows/Mac - Visual Studio 2022, .NET Core 3.x - .NET 6, Server-Side Blazor, ML.NET v1.5 - v1.7, Azure SignalR (optional for massively scaling message communication for Azure deployments)
  • Note: Updated Azure service versions or NuGet package references could work

More Information: